{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-about-an-exponential-amount-of","title":"Learning about an exponential amount of conditional distributions","arxiv_id":"1902.08401","date":"2019-02-22","proceeding":"NeurIPS 2019 12","authors":["Mohamed Ishmael Belghazi","Maxime Oquab","Yann Lecun","David Lopez-Paz"],"abstract":"We introduce the Neural Conditioner (NC), a self-supervised machine able to\nlearn about all the conditional distributions of a random vector $X$. The NC is\na function $NC(x \\cdot a, a, r)$ that leverages adversarial training to match\neach conditional distribution $P(X_r|X_a=x_a)$. After training, the NC\ngeneralizes to sample from conditional distributions never seen, including the\njoint distribution. The NC is also able to auto-encode examples, providing data\nrepresentations useful for downstream classification tasks. In sum, the NC\nintegrates different self-supervised tasks (each being the estimation of a\nconditional distribution) and levels of supervision (partially observed data)\nseamlessly into a single learning experience.","url_abs":"http://arxiv.org/abs/1902.08401v1","url_pdf":"http://arxiv.org/pdf/1902.08401v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-about-an-exponential-amount-of","repo_url":"https://github.com/IshmaelBelghazi/learning_an_exponential_amount_of_conditional_distributions","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.08401","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}